INDEX

Explanations

phrases indicating difficulty or struggle

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akin

-0.20

åĬĽçļĦ

-0.14

hei

-0.13

Tai

-0.13

nen

-0.13

ÐĬ

-0.13

 nada

-0.12

pecific

-0.12

suz

-0.12

Each

-0.12

POSITIVE LOGITS

 many

0.33

many

0.24

us

0.23

 both

0.23

 anyone

0.23

 everyone

0.22

 MANY

0.21

 sure

0.21

 Many

0.20

 most

0.20

Activations Density 0.171%

phrases indicating difficulty or struggle

No Comments

No Known Activations